News for hackers. Stuff that matters.

yoav_hollander

Exactly. I was assuming that the by now the default answer to "LLMs sort-of do this, but not very well" should be "OK, wait a few months".
It is interesting to consider that the Mongol conquests in Asia, much like the Spanish conquests in America, were facilitated by a weapon they did not know they had.
Re:How the U.S. military thinks about AI [audio] on Wednesday January 15, 2020 @01:19PM (#22056803)
Here is a (longish) post I wrote about this issue (mainly from the perspective of verifying autonomous vehicles):

https://blog.foretellix.com/2017/07/06/where-machine-learnin...

Re:Testing distributed systems on Friday May 04, 2018 @12:03PM (#16995626)
This is a really good list. Thanks.
Re:Programming won't be automated, or it already has been on Tuesday July 11, 2017 @10:49AM (#14744623)
Cleanly connecting NNs to contracts / rules is indeed a hard problem, which many people would like to see solved. Please see my post about that [1], and the corresponding HN comment thread [2].

[1] http://blog.foretellix.com/2017/07/06/where-machine-learning...

[2] https://news.ycombinator.com/item?id=14717692

Re:Where machine learning meets rule-based systems on Sunday July 09, 2017 @03:48AM (#14728797)
Right - as far as I know most ANNs _are_ embedded in some pipeline which contains also "regular" SW, and thus by definition there _is_ some way to connect them to a rule-based system.

The only issue is that there is no easy, _natural_ way to do it. For instance, consider the various attempts at adding safety rules to an RL ANN (depicted in fig. 2 in the paper). Say that (in the context of an ANN controlling an Autonomous Vehicle) your ANN decided to do something on the freeway, but the safety rules say "no". There is no easy way to gracefully integrate the rule and ANN: One way is for the rule to disable the ANN's output at this point, take full control and decide what the AV _should_ do. But this leads to duplication and complexity.

So the four solutions I describe take various ways to avoid this problem. They all "work" in a sense, but none does real "integration" of the ANN and the rules (the shield synthesis solution perhaps comes closest). And it looks like you have to invent this kind of solution anew for every new instance of connecting-ANN-to-rules.

And this was just "inserting rules during execution". Then there is the issue of "verifying via rules", and "explaining the rules". It is tough, and I am wondering if there could be some conceptual breakthrough which would make it somewhat easier.

Older »